© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84313
    Prev
    Next
    INDEX
    Explanations

    for the first time

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on numeric expressions (digits, quantities, and statistics).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gegebenen
    -1.38
     любы
    -1.38
    也很
    -1.32
    不断
    -1.28
    recently
    -1.23
     любых
    -1.23
     posled
    -1.23
    镡
    -1.23
    kadang
    -1.23
    最近
    -1.21
    POSITIVE LOGITS
     this
    1.65
     a
    1.64
     two
    1.47
     three
    1.43
     several
    1.39
     other
    1.37
     people
    1.35
     an
    1.34
     after
    1.32
    </h1>
    1.28
    Activations Density 0.033%

    No Known Activations